Lecturer: Magda Gregorova
Fields: Machine Learning, Deep Learning
Content
In this introductory course we will cover the basics of machine learning (ML) targeting specifically the un-initiated audience. If you are not sure what machine learning actually is, if you have never trained an ML model, if for you deep learning means learning in deep sleep and ChatGPT is a result of dark magic, then this course is meant for you. The course will be organized in four sessions where (1) we will begin from the basic concepts of learning from data reviewing the fundamental ideas and building stones of machine learning, (2) we shall discuss some classical ML algorithms which are still the workhorses for solving many practical problems, (3) we shall explore the more modern deep learning approaches based on neural network models, and (4) we shall uncover some of the magic behind ChatGPT by discussing the concepts of deep generative modelling. The field is vast and very fast paced combining mathematics with computer science while spicing it up with ideas coming from physics, neuroscience, and many other areas. While some math cannot be avoided, it is not my ambition to cover all the technicalities of ML. I will rather endeavor to help you build your own picture of the field based on basic understanding of the underlying fundamental ideas and nature your own intuition for data analysis hoping you will become more comfortable and confident when exploring the ML methods in your future work.
Literature
- Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
- Murphy, K. P. (2012). Machine learning: A probabilistic perspective. MIT Press.
- Hastie, T., Tibshirani, R., & Friedman, J. (2001). The Elements of Statistical Learning. Springer New York Inc.
- Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms (1st ed.). Cambridge University Press. https://doi.org/10.1017/CBO9781107298019
- MacKay, D. J. C. (2003). Information theory, inference and learning algorithms. Cambridge University Press.
- Cover, T.M. and Thomas, J.A. (2006) Elements of Information Theory. John Wiley & Sons, Inc., Hoboken.
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
- Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2021). Dive into Deep Learning. ArXiv Preprint ArXiv:2106.11342.
- Prince, S. J. D. (2023). Understanding deep learning. The MIT Press. http://udlbook.com
- Tomczak, J. M. (2022). Deep Generative Modeling. Springer International Publishing. https://doi.org/10.1007/978-3-030-93158-2
Lecturer
Magda Gregorova comes from Prague, Czech Republic, where she obtained her Master‘s degree in Statistics (2001) from the University of Economics. She started her career as an applied statistician in the Czech National Bank, where she headed a technical unit on financial statistics and collaborated closely with the ECB and the IMF. After several years in banking she has decided to follow an international career and joined Eurocontrol, the European Organization for the Safety of Air Navigation based in Brussels, Belgium, as a statistical analyst and forecaster. She then moved to Geneva, Switzerland, where she obtained in 2018 a PhD in machine learning from the Computer Science Department of the University of Geneva. She continued as a post-doc in the Data Mining and Machine Learning group of the University of Applied Sciences of Western Switzerland. In 2021 Magda has moved to Germany, where she obtained the research professorship for “Representation and Learning in Artificial Intelligence” at the Faculty of Computer Science and Business Information Systems of the Technical University of Applied Sciences Würzburg-Schweinfurt (THWS). She is a founding member of the THWS research Center for Artificial Intelligence (CAIRO) which she has led from its beginnings in 2022 till mid 2024. Her teaching activities are mainly within the international masters on AI in the areas of deep learning and generative modelling. In her research she focuses on deep unsupervised learning methods for modelling complex high-dimensional distributions and data representations for downstream tasks (https://scholar.google.com/citations?user=68MKCOwAAAAJ&hl=en). In addition to her own research she regularly contributes to the machine learning community through reviewing service (ICML, ICLR, NeurIPS, etc.) and by active participation in outreach and educational events such as IK.
Affiliation: Technische Hochschule Würzburg-Schweinfurt
Homepage: https://fiw.thws.de/en/our-faculty/staff/person/prof-dr-magda-gregorova/